Abstract

Extracting tree skeletons from 3D tree point clouds is challenged by noise and incomplete data. While our prior work (Dobbs et al., in: Iberian conference on pattern recognition and image analysis, Springer, Berlin, pp. 351–362, 2023) introduced a deep learning approach for approximating tree branch medial axes, its robustness against various types of noise has not been thoroughly evaluated. This paper addresses this gap. Specifically, we simulate real-world noise challenges by introducing 3D Perlin noise (to represent subtractive noise) and Gaussian noise (to mimic additive noise). To facilitate this evaluation, we introduce a new synthetic tree point cloud dataset, available at https://github.com/uc-vision/synthetic-trees-II. Our results indicate that our deep learning-based skeletonization method is tolerant to both additive and subtractive noise.

中文翻译：

---

量化鲁棒性：在噪声域中使用智能树进行 3D 树点云骨架化

摘要

从 3D 树点云中提取树骨架面临着噪声和不完整数据的挑战。虽然我们之前的工作（Dobbs 等人，在：伊比利亚模式识别和图像分析会议，施普林格，柏林，第 351-362 页，2023 年）引入了一种用于近似树枝中轴的深度学习方法，但其对各种类型的鲁棒性噪声的影响尚未得到彻底评估。本文解决了这一差距。具体来说，我们通过引入 3D Perlin 噪声（代表减性噪声）和高斯噪声（模拟加性噪声）来模拟现实世界的噪声挑战。为了促进这一评估，我们引入了一个新的合成树点云数据集，可从 https://github.com/uc-vision/synthetic-trees-II 获取。我们的结果表明，我们基于深度学习的骨架化方法能够容忍加性和减性噪声。